Evaluate gene sets identified by SDAN
Wei Sun
2024-07-04
Setup
Check enrichment of gene sets
Read in gene info and gene set assignments
file_tag = sprintf("%s_BL_%s", cell_type_name, graph_weight)
assayed_genes = scan(sprintf("output/gene_list_%s.txt", file_tag),
what = character(), sep="\n")
gene_sets = scan(sprintf("output/name_s_%s.txt", file_tag),
what = character(), sep="\n")
gene_sets = sapply(gene_sets, strsplit, USE.NAMES=FALSE, split=",")
n_genes = sapply(gene_sets, length)
names(n_genes) = NULL
summary(n_genes)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 4.0 23.0 24.0 23.3 25.0 26.0## [1] 40## [1] 4 19 20 22 22 22 22 22 23 23 23 23 23 23 24 24 24 24 24 24 24 24 24 24 25
## [26] 25 25 25 25 25 25 25 25 25 25 25 25 25 25 26Find gene symbols
Find gene symbols from bioMart.
All the gene symbols that can be found in bioMart are
consistent with what we have. So no need to run it.
ensembl = useMart("ensembl", dataset = "hsapiens_gene_ensembl")
gene_BM = getBM(attributes = c("hgnc_symbol", "external_gene_name"),
filters = "external_gene_name",
values = assayed_genes,
mart = ensembl)
length(assayed_genes)
dim(gene_BM)
gene_BM[1:2,]
table(assayed_genes %in% gene_BM$external_gene_name)
t1 = table(gene_BM$external_gene_name)
dup = names(t1)[t1 > 1]
gene_BM[gene_BM$external_gene_name %in% dup,]
table(gene_BM$hgnc_symbol == gene_BM$external_gene_name)
w2kp = which(gene_BM$hgnc_symbol != gene_BM$external_gene_name)
gene_BM[w2kp,]Find gene symbols using the alias2Symbol function from
limma.
a2s = rep(NA, length(assayed_genes))
for(i in 1:length(assayed_genes)){
gi = assayed_genes[i]
ai = alias2Symbol(gi)
if(length(ai) > 1){
print(gi)
print(ai)
}
a2s[i] = ai[1]
}## [1] "HIST1H2BC"
## [1] "H2BC5" "H2BC4"
## [1] "MPP6"
## [1] "MPHOSPH6" "PALS2"
## [1] "MARS"
## [1] "MARS1" "SLA2"
## [1] "SEPT2"
## [1] "SEPTIN6" "SEPTIN2"##
## FALSE TRUE
## 1951 49##
## FALSE TRUE <NA>
## 45 1906 49gene_info = data.table(sym_in_data = assayed_genes, sym_limma = a2s)
gene_info[sym_in_data != sym_limma,]## sym_in_data sym_limma
## 1: ADPRHL2 ADPRS
## 2: AES TLE5
## 3: C12orf45 NOPCHAP1
## 4: C3orf58 DIPK2A
## 5: C6orf99 LINC02901
## 6: CBWD2 ZNG1B
## 7: CXorf57 RADX
## 8: FAM102A EEIG1
## 9: FAM122C PABIR3
## 10: FAM153C FAM153CP
## 11: FAM160A2 FHIP1B
## 12: GRASP TAMALIN
## 13: H2AFX H2AX
## 14: HIST1H2AG H2AC11
## 15: HIST1H2BC H2BC5
## 16: HIST1H2BK H2BC12
## 17: HIST1H2BN H2BC15
## 18: HIST1H3A H3C1
## 19: HIST1H3H H3C10
## 20: HIST1H4C H4C3
## 21: HIST2H2BF H2BC18
## 22: LRMP IRAG2
## 23: MFSD14C MFSD14CP
## 24: MKL1 MRTFA
## 25: MPP6 MPHOSPH6
## 26: RNASEH1-AS1 RNASEH1-DT
## 27: SEPT6 SEPTIN6
## 28: SEPT9 SEPTIN9
## 29: TMEM161B-AS1 TMEM161B-DT
## 30: ARNTL BMAL1
## 31: C6orf106 ILRUN
## 32: C6orf203 MTRES1
## 33: FAM129A NIBAN1
## 34: FAM160B1 FHIP2A
## 35: FAM192A PSME3IP1
## 36: HEXDC HEXD
## 37: HIST1H1E H1-4
## 38: KIAA0100 BLTP2
## 39: KIAA1551 RESF1
## 40: LARS LARS1
## 41: MARS MARS1
## 42: PLA2G16 PLAAT3
## 43: SEPT2 SEPTIN6
## 44: SMIM37 MTLN
## 45: YARS YARS1
## sym_in_data sym_limmagene_info[, gene_symbol := sym_in_data]
gene_info[which(sym_in_data != sym_limma), gene_symbol := sym_limma]
dim(gene_info)## [1] 2000 3## sym_in_data sym_limma gene_symbol
## 1: ABCD3 ABCD3 ABCD3
## 2: ABCG1 ABCG1 ABCG1
## 3: ABHD5 ABHD5 ABHD5
## 4: ABI1 ABI1 ABI1
## 5: ABLIM1 ABLIM1 ABLIM1## t1
## 1 2
## 1998 1## sym_in_data sym_limma gene_symbol
## 1: SEPT6 SEPTIN6 SEPTIN6
## 2: SEPT2 SEPTIN6 SEPTIN6Prepare gene set information
Gene set annotations (by gene symbols) were downloaded from MSigDB website.
gmtfile = list()
gmtfile[["reactome"]] = "../Annotation/c2.cp.reactome.v2023.2.Hs.symbols.gmt"
gmtfile[["go_bp"]] = "../Annotation/c5.go.bp.v2023.2.Hs.symbols.gmt"
gmtfile[["immune"]] = "../Annotation/c7.all.v2023.2.Hs.symbols.gmt"
pathways = list()
for(k1 in names(gmtfile)){
pathways[[k1]] = gmtPathways(gmtfile[[k1]])
}
names(pathways)## [1] "reactome" "go_bp" "immune"## reactome go_bp immune
## 1692 7647 5219Filter gene sets for size between 10 and 500.
## $reactome
## 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
## 5.0 7.0 9.0 12.0 17.0 23.0 31.0 44.0 71.8 120.9 1463.0
##
## $go_bp
## 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
## 5.0 6.0 8.0 10.0 14.0 19.0 29.0 46.0 80.8 183.0 1966.0
##
## $immune
## 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
## 5 162 193 197 199 199 200 200 200 200 1992Conduct enrichment analysis
## [1] 2000 3max_n2kp = 10
goseq_res = NULL
for(k in 1:length(gene_sets)){
if(length(gene_sets[[k]]) < 10) { next }
print(k)
set_k = paste0("set_", k)
print(gene_sets[[k]])
genes = gene_info$sym_in_data %in% gene_sets[[k]]
names(genes) = gene_info$gene_symbol
table(genes)
pwf = nullp(genes, "hg38", "geneSymbol")
for(k1 in names(pathways)){
p1 = pathways[[k1]]
res1 = goseq(pwf, "hg38", "geneSymbol",
gene2cat=goseq:::reversemapping(p1))
res1$FDR = p.adjust(res1$over_represented_pvalue, method="BH")
nD = sum(res1$FDR < 0.1)
if(nD > 0){
res1 = res1[order(res1$FDR),][1:min(nD, max_n2kp),]
res1$category = gsub("REACTOME_|GOBP_", "", res1$category)
res1$category = gsub("_", " ", res1$category)
res1$category = tolower(res1$category)
res1$category = substr(res1$category, start=1, stop=81)
goseq_res[[set_k]][[k1]] = res1
}
}
}## [1] 1
## [1] "ADK" "KIF9" "SNHG7" "UPF3A" "AP3M2" "APBB1IP"
## [7] "ATXN7L3B" "BROX" "C2orf68" "CYTIP" "ENY2" "IFITM2"
## [13] "IRAK4" "PKNOX1" "PLAC8" "PRMT2" "SDR39U1" "SEC14L1"
## [19] "SESN3" "SETD5" "SIGIRR" "STK17B"
## [1] 2
## [1] "CCM2" "CHURC1" "DNAAF2" "EVI2B" "FCER1G" "LEPROTL1"
## [7] "NMT2" "PTGER4" "RNF220" "SCPEP1" "SERTAD1" "SFI1"
## [13] "SNX18" "TMEM107" "TNFRSF25" "APOBEC3G" "EMP3" "FAM53B"
## [19] "KLRG1" "LAG3" "SCAMP4" "SPOCK2" "UBR2"
## [1] 3
## [1] "AC008105.3" "AC093323.1" "AK5" "AL359220.1" "ARRDC2"
## [6] "BOLA2-SMG1P6" "COQ8A" "GPCPD1" "IGLV1-44" "JCHAIN"
## [11] "LINC01215" "LRMP" "LST1" "MDS2" "MFSD14C"
## [16] "MUC20-OT1" "NAA16" "PLCL1" "SPART" "TMEM161B-AS1"
## [21] "TRAV38-2DV8" "TRBV7-3" "ZNF600" "ZNF749" "ZNF862"
## [1] 5
## [1] "AC007952.4" "AC013264.1" "AC025171.2" "AC087239.1" "AC245014.3"
## [6] "AL138963.3" "ANXA2R" "DELE1" "IGKV3-20" "JAML"
## [11] "LRRC8C-DT" "LRRN3" "NR4A2" "SCML4" "SNHG8"
## [16] "ST7L" "TBCC" "TMEM71" "TRAV8-6" "TRBV28"
## [21] "TRBV5-4" "WASHC4" "ZFP14" "ZNF506" "MATK"
## [1] 6
## [1] "AC145124.1" "ARHGAP15" "C12orf29" "COX10" "CST3"
## [6] "DPYD" "ERAP2" "IGLV2-14" "KCNK6" "TOMM7"
## [11] "TRAV12-2" "TRAV13-2" "TRAV21" "TRAV41" "TRBC1"
## [16] "TRBC2" "TRBV6-2" "TRBV6-6" "TSPOAP1-AS1" "TTC39C"
## [21] "UCP2" "CCL5" "CCR4" "FRMD4B" "GZMA"
## [1] 7
## [1] "AC009061.2" "AMD1" "CD96" "COA1" "HELQ"
## [6] "LDLRAP1" "RNASEK" "ARID5B" "CARD11" "CCDC112"
## [11] "CHD6" "COX17" "CRTC3" "ERICH1" "GON4L"
## [16] "KIAA1551" "KIF3B" "MIER1" "NADSYN1" "NBEAL2"
## [21] "SLC23A2" "STK10" "TCF25" "TRAC" "ZNF267"
## [1] 8
## [1] "ANAPC4" "BTG1" "BTG2" "CHD2" "EIF1" "EPHB6"
## [7] "FBXL3" "LYRM7" "PHC1" "PLK2" "PNRC1" "PPIL3"
## [13] "SFMBT1" "ZFP36L1" "CCDC12" "CGGBP1" "DPP7" "GPHN"
## [19] "PCGF5" "PUS7L" "SMAP1" "SREK1IP1"
## [1] 9
## [1] "ABHD5" "ATG13" "CD38" "FCGR3A" "LAX1" "MMP24OS"
## [7] "ODF2L" "PNPLA2" "RASA2" "RCSD1" "SNRK" "TESPA1"
## [13] "TMC8" "TRAV23DV6" "TRAV8-2" "TUBD1" "TUBE1" "ZBTB25"
## [19] "HSH2D" "IFI44" "IFI44L" "OAS1" "TRAT1"
## [1] 10
## [1] "ABCC10" "ABHD3" "AC116407.2" "AC118549.1" "ADTRP"
## [6] "C20orf204" "CARMIL2" "CFD" "FAAH2" "GPR132"
## [11] "HRH2" "LRRC58" "MIAT" "NORAD" "NRDC"
## [16] "OSM" "PCSK1N" "SLF2" "SLFN12L" "SPATA13"
## [21] "TOMM70" "TRANK1" "UBALD2" "Z93930.2" "ZFYVE28"
## [1] 11
## [1] "BDH1" "CCR6" "CD48" "LCLAT1" "PTPRCAP" "RNF139"
## [7] "SLC12A6" "SLC25A25" "TRAM1" "ATP8B2" "CD2" "CD58"
## [13] "CMTM6" "GIMAP4" "HM13" "LPCAT3" "LPCAT4" "LPGAT1"
## [19] "SLC12A9"
## [1] 12
## [1] "AC119396.1" "AF213884.3" "AL118516.1" "AL627171.1" "AL645728.1"
## [6] "C12orf57" "C6orf99" "CHRM3-AS2" "CSKMT" "EGR1"
## [11] "HIPK1-AS1" "HIST1H2BC" "ILF3-DT" "LINC00649" "LINC01550"
## [16] "METTL21A" "MID1IP1" "NPIPB11" "NUP58" "ORC4"
## [21] "TC2N" "TMEM154" "TRABD2A" "TMEM175"
## [1] 13
## [1] "AKT3" "C12orf45" "C1orf43" "EPHX2" "GTPBP6" "IP6K2"
## [7] "LBH" "NR1D1" "NR1D2" "PAPOLG" "PDCD7" "PDE3B"
## [13] "PHLDA1" "PPP1R15B" "TMEM63A" "TNFAIP8" "TTC3" "DHX29"
## [19] "EAPP" "EHMT1" "POGLUT1" "SPTLC2" "TCIRG1"
## [1] 14
## [1] "ACADSB" "ACSS1" "ANKH" "ARID4A" "ARMH1" "C7orf31"
## [7] "CAMK4" "CFAP36" "CTSF" "DAPP1" "FAM153C" "FCMR"
## [13] "FOSB" "FYB1" "HIST1H4C" "IER2" "IFRD1" "ING2"
## [19] "MTRNR2L12" "MXD1" "PLEKHM1" "RGCC" "TGIF1" "YY1AP1"
## [1] 15
## [1] "CHIC2" "DHRS3" "ADGRE5" "AKNA" "C12orf75"
## [6] "CARD16" "CD69" "GRK2" "KANSL1-AS1" "KIAA0040"
## [11] "MT1X" "MTRNR2L8" "NAA38" "NBDY" "NDUFC1"
## [16] "NSD3" "PAXX" "PTGER2" "PUM3" "RASAL3"
## [21] "TRAV29DV5" "TRBV12-3" "TSPAN32" "TUT4" "USP30-AS1"
## [1] 16
## [1] "AC015982.1" "AC027644.3" "AC084033.3" "AC097376.2" "AL135791.1"
## [6] "ARF4-AS1" "ARL4A" "CERNA1" "CHMP7" "FAM102A"
## [11] "FAM122C" "GOLGA8B" "IL23A" "LETM2" "LINC02265"
## [16] "LINC02273" "NDUFV2-AS1" "NOCT" "NPIPB5" "NSMCE3"
## [21] "PRR7" "RGS1" "THAP9-AS1" "ATAD2B" "NUP160"
## [1] 17
## [1] "AKIRIN1" "AKIRIN2" "GIMAP8" "OSER1" "PCMTD2" "PYROXD1" "RABL2B"
## [8] "STMN3" "TECPR1" "ZFX" "ZNF140" "CAMTA2" "DOCK11" "NDUFA3"
## [15] "NRROS" "OAS2" "PPP2R3C" "PSMB9" "RNF19A" "SRP54" "TBC1D14"
## [22] "TRAPPC8" "UBA7" "UTP25"
## [1] 18
## [1] "CD28" "DBP" "PECAM1" "BATF" "CD320" "CISH" "CMIP"
## [8] "FBXO9" "G2E3" "IFI35" "IL2RB" "IL2RG" "IL32" "INPP5D"
## [15] "MYOM2" "NQO2" "P4HTM" "RAPGEF1" "SLC35A2" "TIPARP" "UGCG"
## [22] "ZNF276" "ZNF708"
## [1] 19
## [1] "AC025159.1" "AC087623.3" "COQ7" "EFCAB2" "ENOSF1"
## [6] "FOXN3" "GADD45B" "GRASP" "KCNQ1OT1" "MBD6"
## [11] "NSUN6" "ODC1" "SLC22A17" "SNHG12" "TBCCD1"
## [16] "TCTA" "YPEL2" "AC022916.1" "ANKAR" "AREG"
## [21] "ITK" "SNHG9" "TAF4B" "TNFRSF4" "UBE3B"
## [1] 20
## [1] "C16orf74" "C3orf58" "CCDC141" "CCDC66" "CEP95" "CHMP1B"
## [7] "FAM117B" "IL6R" "MAST4" "PHYH" "PIK3IP1" "PNISR"
## [13] "RCAN3" "RIC1" "SH3YL1" "SLC44A1" "STX16" "TBCK"
## [19] "TSC22D2" "WARS2" "ADAM19" "C12orf4" "HELB" "WDR7"
## [1] 21
## [1] "ADPRHL2" "BTN3A1" "LTA4H" "PITPNA-AS1" "TMEM245"
## [6] "UTP6" "ALOX5AP" "APOL1" "APOL6" "BTN3A2"
## [11] "BUD23" "CTSW" "ECPAS" "GBP1" "GBP3"
## [16] "GBP5" "GZMM" "HEXDC" "MCTP2" "NCBP3"
## [21] "PEX11B" "SP140" "TAOK3" "TGFBR3" "TMEM62"
## [1] 22
## [1] "RBKS" "ZSCAN18" "ABHD2" "APH1B" "CITED4" "DDX3Y"
## [7] "EIF1AY" "GABPB2" "IL21R" "KDM5D" "KHNYN" "KIF21B"
## [13] "RNF157" "RPS4Y1" "RTKN2" "SBNO2" "SLC25A37" "SUSD6"
## [19] "TENT5C" "TMEM156" "TTTY15" "UTY"
## [1] 23
## [1] "ASAH1" "HVCN1" "MYADM" "OXLD1" "AGAP2" "ARHGAP4" "BLOC1S6"
## [8] "CD55" "CD7" "DIP2A" "GGCX" "IFNAR1" "IFNGR2" "MORC3"
## [15] "NME3" "NPDC1" "PIEZO1" "PSME2" "REXO2" "SCAF8" "TIMP1"
## [22] "UQCC2" "ZDHHC20"
## [1] 24
## [1] "COL18A1" "DALRD3" "NECAP2" "ADGRG1" "ARHGEF3" "ARL4C"
## [7] "COL6A3" "COLGALT1" "CX3CR1" "FGFBP2" "LAIR2" "LINC01871"
## [13] "LPIN1" "LPIN2" "LY96" "PCED1B" "PLEK" "RAP1GAP2"
## [19] "RNPEPL1" "SP140L" "TCAF2" "TTC16" "VPS13D" "ZNF683"
## [1] 25
## [1] "C6orf62" "CCNH" "COQ10B" "DGKA" "ERCC5" "FHIT" "INPP4B"
## [8] "KLHL24" "LEF1" "MYNN" "NFYB" "TCF7" "TPP2" "ACAP1"
## [15] "CREBZF" "ETNK1" "NARF" "NFE2L1" "PPRC1" "RHOH" "STAT4"
## [22] "TGS1" "VPS36" "XBP1"
## [1] 26
## [1] "AP002360.1" "ATG9B" "CITED2" "FBXO3" "KIAA1328"
## [6] "MAML2" "MBNL2" "MHENCR" "MLXIP" "MMP28"
## [11] "MTERF4" "PDE7A" "PLCD1" "RAB33B" "RETREG1"
## [16] "SLC8B1" "TAGAP" "THAP6" "TRAV8-3" "TSPYL4"
## [21] "WHAMM" "WSB1" "XIST" "ZNF10" "CCDC43"
## [1] 27
## [1] "CBR3" "DPEP2" "GGT7" "LIMS1" "NEU1" "SERTAD2"
## [7] "SLC25A32" "USP3" "ZNF677" "B3GALT4" "FKBP11" "FUT11"
## [13] "GALNS" "GZMB" "PARVG" "PLAA" "RSU1" "SACS"
## [19] "SH3BGRL3" "SRGN" "ST6GAL1" "TRIB2"
## [1] 28
## [1] "MZF1" "NSMAF" "YPEL5" "C4orf48" "CROT" "DENND4B" "EFR3A"
## [8] "EIF2AK4" "GNLY" "ISG20" "KCNAB2" "KLF9" "KLHDC4" "LTBP4"
## [15] "NEK9" "NLRC5" "NT5C" "PDE4B" "PREP" "PREX1" "PTPRE"
## [22] "RCBTB2" "SYTL1" "ZNF236" "ZNF292"
## [1] 29
## [1] "ABCG1" "AIF1" "ARHGAP9" "CD40LG" "CRLF3"
## [6] "DNASE1" "GIMAP1" "HIST1H3H" "IPCEF1" "JPX"
## [11] "KLF7" "LIPT1" "LYRM9" "NABP1" "NBPF14"
## [16] "NUAK2" "NUDT4" "RNASEH1-AS1" "SLC7A6" "SPIDR"
## [21] "STARD10" "STK17A" "ZFAS1" "ZMAT1" "ZNF84"
## [1] 30
## [1] "ATAD1" "CDC37L1" "COG5" "DIP2B" "DSE" "FCN1"
## [7] "HIVEP2" "HOXB2" "IGKV1-5" "IL16" "KLHL6" "LRRC8D"
## [13] "PARP16" "PITPNC1" "RAB37" "RPS26" "SIMC1" "SLC25A33"
## [19] "SLC26A11" "FAM129A" "GNPTAB" "JAKMIP1" "MT2A" "SERTAD3"
## [25] "SMPD2"
## [1] 31
## [1] "LINC00623" "POLD4" "TRAV12-1" "TRAV14DV4" "WAPL"
## [6] "ZNF91" "AC020915.3" "C1orf162" "CCL4" "CD300A"
## [11] "FCRL6" "GPR65" "HACD3" "MESD" "MFSD14A"
## [16] "NNT-AS1" "PARP11" "S100A12" "S1PR5" "SMIM37"
## [21] "THUMPD3-AS1" "TM2D1" "TMEM138" "TRBV6-1" "TSPAN14"
## [26] "TTC38"
## [1] 32
## [1] "AC004687.1" "AC004854.2" "AC016405.3" "AC020911.2" "AC023157.3"
## [6] "AC025164.1" "AC025171.3" "AC083880.1" "AC091271.1" "AC103591.3"
## [11] "AL121944.1" "AL139246.5" "AL357060.1" "AL451085.1" "ATP2B1-AS1"
## [16] "BX284668.6" "ID3" "LINC01465" "MATR3-1" "MZF1-AS1"
## [21] "NPIPB4" "OSER1-DT" "PARP8" "SDR42E2" "Z93241.1"
## [1] 33
## [1] "IER3" "PECR" "PPP2R5C" "ARHGAP10" "C1orf21" "CARD8-AS1"
## [7] "CST7" "DTX3L" "GMFB" "IGLV3-25" "IRF9" "MYO1F"
## [13] "NKG7" "ODF3B" "PARP14" "PARP9" "PEX26" "PLA2G16"
## [19] "PPP2R5B" "PTGDR" "RSAD2" "SLA" "TNFRSF18" "ZBP1"
## [1] 34
## [1] "ABLIM1" "ABTB1" "ATP5MG" "FBXO8" "HDHD2" "LIMD2"
## [7] "LINC00861" "LTB" "MCUB" "METAP1" "NOP53" "NT5DC1"
## [13] "PCNP" "RACK1" "SGSM3" "SMDT1" "TBC1D10C" "TBPL1"
## [19] "TRAV9-2" "CDK2AP2" "FGR" "NUS1" "PARP4" "S100A11"
## [1] 35
## [1] "CSRNP1" "GATA3" "KANSL2" "KDM6A" "NR4A3" "STK19" "TOB2"
## [8] "ZNF490" "ASCL2" "BHLHE40" "CNOT4" "GCN1" "KANSL1" "KMT2B"
## [15] "KMT2C" "PHF20" "PHF20L1" "RECK" "SH3BP5" "SYNE1" "TBX21"
## [22] "TNFSF10"
## [1] 36
## [1] "AC245297.3" "ADA2" "AL133415.1" "C1GALT1" "ERVK3-1"
## [6] "GIMAP6" "GZMK" "HEATR5B" "KLF10" "LEPROT"
## [11] "OTULINL" "SLC25A38" "TOX" "TRAV25" "TRBV6-5"
## [16] "BISPR" "CRIP2" "GAB3" "MIR4435-2HG" "MX2"
## [21] "MYBL1" "MYO1G" "SAMD9L" "SPON2" "SYNRG"
## [1] 37
## [1] "CDC42SE2" "FAM118A" "IER5" "KLF12" "MAP3K8" "MTO1"
## [7] "PRKCH" "RSRP1" "SENP7" "SLC12A7" "TBC1D7" "TCP11L2"
## [13] "TMEM204" "TTC31" "UBL3" "XRRA1" "ZFAND5" "ZNF831"
## [19] "CAST" "SAMD9" "SDF2" "TRIM22" "XAF1" "ZBTB8OS"
## [1] 38
## [1] "CD82" "FAM227B" "HIPK1" "IL27RA" "NEK1" "PLK3" "ST3GAL1"
## [8] "BCL9L" "DIAPH2" "FNDC3B" "GCA" "GIMAP7" "ITGAL" "LCP1"
## [15] "LY6E" "PHF11" "PHF23" "RBSN" "ROMO1" "TYMP"
## [1] 39
## [1] "COQ10A" "SLC2A3" "ZC3H12A" "ZC3H12D" "ZHX2"
## [6] "AC016831.7" "CCDC88B" "CEMIP2" "CRYBG1" "CTBS"
## [11] "DDIT4" "FRY" "GPRIN3" "ICOS" "KLF6"
## [16] "LTBP3" "NEAT1" "NFKBIZ" "PRDM2" "RNF145"
## [21] "RNMT" "SLC9A8" "TOB1" "ZNF101"
## [1] 40
## [1] "CLK4" "EPB41" "EVL" "FLI1" "LETMD1" "MALAT1" "NOSIP"
## [8] "POLL" "RGS10" "SEPT6" "SH2D1A" "SS18" "STARD7" "ZNF821"
## [15] "ACAP2" "ACAP3" "AFF1" "KMT2E" "LRRFIP1" "MLLT10" "PIM2"
## [22] "PVT1" "SELL"
for(n1 in names(goseq_res)){
k = as.numeric(gsub("set_", "", n1))
print(n1)
print(gene_sets[[k]])
print(goseq_res[[n1]])
}## [1] "set_9"
## [1] "ABHD5" "ATG13" "CD38" "FCGR3A" "LAX1" "MMP24OS"
## [7] "ODF2L" "PNPLA2" "RASA2" "RCSD1" "SNRK" "TESPA1"
## [13] "TMC8" "TRAV23DV6" "TRAV8-2" "TUBD1" "TUBE1" "ZBTB25"
## [19] "HSH2D" "IFI44" "IFI44L" "OAS1" "TRAT1"
## $immune
## category
## 5062 querec pbmc yf 17d vaccine age 18 45yo 3dy up
## 5063 querec pbmc yf 17d vaccine age 18 45yo 7dy up
## 2462 gse27241 ctrl vs digoxin treated rorgt ko cd4 tcell in th17 polarizing conditions
## 4972 howard t cell inact monov influenza a indonesia 05 2005 h5n1 age 18 49yo 1dy up
## 5102 zak pbmc mrkad5 hiv 1 gag pol nef age 20 50yo 3dy up
## 1289 gse17974 il4 and anti il12 vs untreated 24h act cd4 tcell dn
## over_represented_pvalue under_represented_pvalue numDEInCat numInCat
## 5062 7.573764e-06 0.9999998 5 27
## 5063 7.573764e-06 0.9999998 5 27
## 2462 8.505566e-05 0.9999971 4 22
## 4972 9.660053e-05 0.9999965 4 23
## 5102 1.058165e-04 0.9999937 5 45
## 1289 1.113896e-04 0.9999933 5 45
## FDR
## 5062 0.01933582
## 5063 0.01933582
## 2462 0.09479256
## 4972 0.09479256
## 5102 0.09479256
## 1289 0.09479256
##
## [1] "set_11"
## [1] "BDH1" "CCR6" "CD48" "LCLAT1" "PTPRCAP" "RNF139"
## [7] "SLC12A6" "SLC25A25" "TRAM1" "ATP8B2" "CD2" "CD58"
## [13] "CMTM6" "GIMAP4" "HM13" "LPCAT3" "LPCAT4" "LPGAT1"
## [19] "SLC12A9"
## $reactome
## category over_represented_pvalue
## 398 glycerophospholipid biosynthesis 2.354282e-05
## 721 phospholipid metabolism 1.799579e-04
## 31 acyl chain remodelling of pe 4.096445e-04
## 34 acyl chain remodelling of ps 4.096445e-04
## 32 acyl chain remodelling of pg 4.097818e-04
## under_represented_pvalue numDEInCat numInCat FDR
## 398 0.9999995 4 16 0.02827492
## 721 0.9999928 4 26 0.09842958
## 31 0.9999986 2 3 0.09842958
## 34 0.9999986 2 3 0.09842958
## 32 0.9999986 2 3 0.09842958
##
## $go_bp
## category over_represented_pvalue
## 2409 phosphatidylethanolamine acyl chain remodeling 3.028192e-06
## 2412 phosphatidylglycerol metabolic process 7.512040e-06
## under_represented_pvalue numDEInCat numInCat FDR
## 2409 1 3 4 0.01448384
## 2412 1 3 5 0.01796504
##
## $immune
## category
## 1106 gse17721 lps vs pam3csk4 1h bmdc up
## 3991 gse41867 memory vs exhausted cd8 tcell day30 lcmv dn
## over_represented_pvalue under_represented_pvalue numDEInCat numInCat
## 1106 3.056575e-05 0.9999992 4 20
## 3991 3.718477e-05 0.9999983 5 42
## FDR
## 1106 0.09493271
## 3991 0.09493271
##
## [1] "set_18"
## [1] "CD28" "DBP" "PECAM1" "BATF" "CD320" "CISH" "CMIP"
## [8] "FBXO9" "G2E3" "IFI35" "IL2RB" "IL2RG" "IL32" "INPP5D"
## [15] "MYOM2" "NQO2" "P4HTM" "RAPGEF1" "SLC35A2" "TIPARP" "UGCG"
## [22] "ZNF276" "ZNF708"
## $reactome
## category over_represented_pvalue
## 491 interleukin 3 interleukin 5 and gm csf signaling 8.564168e-06
## 498 interleukin receptor shc signaling 5.799668e-05
## 995 signaling by interleukins 6.607657e-05
## 486 interleukin 2 family signaling 2.608409e-04
## under_represented_pvalue numDEInCat numInCat FDR
## 491 0.9999999 4 12 0.01028557
## 498 0.9999994 3 7 0.02645265
## 995 0.9999946 7 92 0.02645265
## 486 0.9999946 3 11 0.07831747
##
## [1] "set_21"
## [1] "ADPRHL2" "BTN3A1" "LTA4H" "PITPNA-AS1" "TMEM245"
## [6] "UTP6" "ALOX5AP" "APOL1" "APOL6" "BTN3A2"
## [11] "BUD23" "CTSW" "ECPAS" "GBP1" "GBP3"
## [16] "GBP5" "GZMM" "HEXDC" "MCTP2" "NCBP3"
## [21] "PEX11B" "SP140" "TAOK3" "TGFBR3" "TMEM62"
## $go_bp
## category
## 693 disruption of anatomical structure in another organism
## over_represented_pvalue under_represented_pvalue numDEInCat numInCat
## 693 6.700668e-07 1 5 17
## FDR
## 693 0.003204929
##
## $immune
## category
## 892 gse1740 mcsf vs mcsf and ifng day2 derived macrophage up
## 2497 gse2770 il12 and tgfb vs il4 treated act cd4 tcell 48h dn
## 895 gse1740 unstim vs ifna stimulated mcsf derived macrophage dn
## 4959 howard b cell inact monov influenza a indonesia 05 2005 h5n1 age 18 49yo 1dy up
## 5035 nakaya pbmc imuvac male age 14 27yo 1d postboost vs 0dy preimm tiv up
## 509 gse1432 1h vs 24h ifng microglia dn
## 4963 howard monocyte inact monov influenza a indonesia 05 2005 h5n1 age 18 49yo 1dy up
## 152 gse1112 hy cd8ab vs hy cd8aa thymocyte rtoc culture up
## 4966 howard neutrophil inact monov influenza a indonesia 05 2005 h5n1 age 18 49yo 3dy
## over_represented_pvalue under_represented_pvalue numDEInCat numInCat
## 892 1.905730e-06 0.9999999 6 32
## 2497 7.532723e-06 0.9999996 6 40
## 895 1.530649e-05 0.9999991 6 45
## 4959 6.683699e-05 0.9999992 3 7
## 5035 6.685649e-05 0.9999992 3 7
## 509 7.497802e-05 0.9999942 6 59
## 4963 1.194293e-04 0.9999899 6 64
## 152 1.368987e-04 0.9999913 5 41
## 4966 1.540312e-04 0.9999899 5 42
## FDR
## 892 0.009730658
## 2497 0.019231041
## 895 0.026051649
## 4959 0.063806293
## 5035 0.063806293
## 509 0.063806293
## 4963 0.087115163
## 152 0.087375595
## 4966 0.087387036
##
## [1] "set_24"
## [1] "COL18A1" "DALRD3" "NECAP2" "ADGRG1" "ARHGEF3" "ARL4C"
## [7] "COL6A3" "COLGALT1" "CX3CR1" "FGFBP2" "LAIR2" "LINC01871"
## [13] "LPIN1" "LPIN2" "LY96" "PCED1B" "PLEK" "RAP1GAP2"
## [19] "RNPEPL1" "SP140L" "TCAF2" "TTC16" "VPS13D" "ZNF683"
## $reactome
## category over_represented_pvalue
## 167 collagen biosynthesis and modifying enzymes 2.263001e-05
## 170 collagen formation 8.391148e-05
## 168 collagen chain trimerization 1.166352e-04
## 1170 triglyceride biosynthesis 1.197099e-04
## 1073 synthesis of pe 3.589348e-04
## under_represented_pvalue numDEInCat numInCat FDR
## 167 0.9999998 3 6 0.02717864
## 170 0.9999989 3 9 0.03594291
## 168 1.0000000 2 2 0.03594291
## 1170 1.0000000 2 2 0.03594291
## 1073 0.9999988 2 3 0.08621613
##
## [1] "set_25"
## [1] "C6orf62" "CCNH" "COQ10B" "DGKA" "ERCC5" "FHIT" "INPP4B"
## [8] "KLHL24" "LEF1" "MYNN" "NFYB" "TCF7" "TPP2" "ACAP1"
## [15] "CREBZF" "ETNK1" "NARF" "NFE2L1" "PPRC1" "RHOH" "STAT4"
## [22] "TGS1" "VPS36" "XBP1"
## $immune
## category over_represented_pvalue
## 2996 gse32901 th1 vs th17 enriched cd4 tcell up 1.917639e-05
## under_represented_pvalue numDEInCat numInCat FDR
## 2996 0.9999989 6 49 0.09791465
##
## [1] "set_27"
## [1] "CBR3" "DPEP2" "GGT7" "LIMS1" "NEU1" "SERTAD2"
## [7] "SLC25A32" "USP3" "ZNF677" "B3GALT4" "FKBP11" "FUT11"
## [13] "GALNS" "GZMB" "PARVG" "PLAA" "RSU1" "SACS"
## [19] "SH3BGRL3" "SRGN" "ST6GAL1" "TRIB2"
## $reactome
## category over_represented_pvalue
## 105 blood group systems biosynthesis 0.0001173633
## 42 aflatoxin activation and detoxification 0.0001262795
## 101 biological oxidations 0.0001807014
## under_represented_pvalue numDEInCat numInCat FDR
## 105 1.0000000 2 2 0.07234081
## 42 1.0000000 2 2 0.07234081
## 101 0.9999968 3 11 0.07234081
##
## [1] "set_33"
## [1] "IER3" "PECR" "PPP2R5C" "ARHGAP10" "C1orf21" "CARD8-AS1"
## [7] "CST7" "DTX3L" "GMFB" "IGLV3-25" "IRF9" "MYO1F"
## [13] "NKG7" "ODF3B" "PARP14" "PARP9" "PEX26" "PLA2G16"
## [19] "PPP2R5B" "PTGDR" "RSAD2" "SLA" "TNFRSF18" "ZBP1"
## $immune
## category
## 1456 gse19888 adenosine a3r inh vs act with inhibitor pretreatment in mast cell up
## 1460 gse19888 adenosine a3r inh vs tcell membranes act mast cell up
## 3886 gse40666 untreated vs ifna stim stat1 ko cd8 tcell 90min up
## 4432 gse5589 lps and il10 vs lps and il6 stim il6 ko macrophage 45min up
## 3962 gse41867 day15 effector vs day30 exhausted cd8 tcell lcmv clone13 up
## 379 gse13485 ctrl vs day7 yf17d vaccine pbmc dn
## 4965 howard neutrophil inact monov influenza a indonesia 05 2005 h5n1 age 18 49yo 1dy
## 2412 gse26890 cxcr1 neg vs pos effector cd8 tcell up
## 2348 gse26030 th1 vs th17 day5 post polarization up
## 3275 gse36078 wt vs il1r ko lung dc dn
## over_represented_pvalue under_represented_pvalue numDEInCat numInCat
## 1456 1.598740e-06 0.9999999 7 49
## 1460 2.692155e-06 0.9999999 7 53
## 3886 3.504527e-06 0.9999999 6 35
## 4432 5.367951e-06 0.9999997 7 59
## 3962 1.159691e-05 0.9999994 6 47
## 379 1.540305e-05 0.9999989 7 68
## 4965 2.016917e-05 0.9999981 8 104
## 2412 3.365894e-05 0.9999978 6 53
## 2348 4.030853e-05 0.9999973 6 52
## 3275 4.338874e-05 0.9999979 5 36
## FDR
## 1456 0.005964705
## 1460 0.005964705
## 3886 0.005964705
## 4432 0.006852189
## 3962 0.011842768
## 379 0.013107997
## 4965 0.014711966
## 2412 0.021182552
## 2348 0.021182552
## 3275 0.021182552
##
## [1] "set_35"
## [1] "CSRNP1" "GATA3" "KANSL2" "KDM6A" "NR4A3" "STK19" "TOB2"
## [8] "ZNF490" "ASCL2" "BHLHE40" "CNOT4" "GCN1" "KANSL1" "KMT2B"
## [15] "KMT2C" "PHF20" "PHF20L1" "RECK" "SH3BP5" "SYNE1" "TBX21"
## [22] "TNFSF10"
## $reactome
## category
## 352 formation of wdr5 containing histone modifying complexes
## 295 epigenetic regulation of gene expression
## 153 chromatin modifying enzymes
## over_represented_pvalue under_represented_pvalue numDEInCat numInCat
## 352 1.711024e-10 1.0000000 7 16
## 295 5.818645e-08 1.0000000 7 38
## 153 4.107397e-05 0.9999975 6 61
## FDR
## 352 2.054940e-07
## 295 3.494096e-05
## 153 1.644328e-02
##
## $go_bp
## category
## 1115 histone modification
## 1112 histone h3 k4 methylation
## 1114 histone methylation
## 2369 peptidyl lysine methylation
## 2689 positive regulation of histone methylation
## 3476 regulation of dosage compensation by inactivation of x chromosome
## 3580 regulation of histone h3 k4 methylation
## 3147 protein methylation
## 3581 regulation of histone methylation
## 1113 histone h4 acetylation
## over_represented_pvalue under_represented_pvalue numDEInCat numInCat
## 1115 7.962431e-07 1.0000000 6 29
## 1112 2.131837e-06 1.0000000 4 8
## 1114 3.822025e-06 1.0000000 4 10
## 2369 1.022126e-05 0.9999998 4 12
## 2689 1.771221e-05 0.9999999 3 5
## 3476 1.771221e-05 0.9999999 3 5
## 3580 1.771221e-05 0.9999999 3 5
## 3147 3.004498e-05 0.9999993 4 15
## 3581 3.708037e-05 0.9999997 3 7
## 1113 6.288136e-05 1.0000000 2 2
## FDR
## 1115 0.003808431
## 1112 0.005098289
## 1114 0.006093582
## 2369 0.012102503
## 2689 0.012102503
## 3476 0.012102503
## 3580 0.012102503
## 3147 0.017963144
## 3581 0.019706158
## 1113 0.030076153
##
## [1] "set_36"
## [1] "AC245297.3" "ADA2" "AL133415.1" "C1GALT1" "ERVK3-1"
## [6] "GIMAP6" "GZMK" "HEATR5B" "KLF10" "LEPROT"
## [11] "OTULINL" "SLC25A38" "TOX" "TRAV25" "TRBV6-5"
## [16] "BISPR" "CRIP2" "GAB3" "MIR4435-2HG" "MX2"
## [21] "MYBL1" "MYO1G" "SAMD9L" "SPON2" "SYNRG"
## $reactome
## category
## 239 diseases associated with o glycosylation of proteins
## 682 o linked glycosylation
## over_represented_pvalue under_represented_pvalue numDEInCat numInCat
## 239 6.447454e-05 0.9999999 2 3
## 682 1.245271e-04 0.9999997 2 4
## FDR
## 239 0.07477851
## 682 0.07477851Session information
## used (Mb) gc trigger (Mb) limit (Mb) max used (Mb)
## Ncells 8958389 478.5 16391124 875.4 NA 16391124 875.4
## Vcells 19173826 146.3 60252964 459.7 65536 77218972 589.2## R version 4.2.3 (2023-03-15)
## Platform: aarch64-apple-darwin20 (64-bit)
## Running under: macOS Ventura 13.4.1
##
## Matrix products: default
## BLAS: /Library/Frameworks/R.framework/Versions/4.2-arm64/Resources/lib/libRblas.0.dylib
## LAPACK: /Library/Frameworks/R.framework/Versions/4.2-arm64/Resources/lib/libRlapack.dylib
##
## locale:
## [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
##
## attached base packages:
## [1] stats4 stats graphics grDevices utils datasets methods
## [8] base
##
## other attached packages:
## [1] TxDb.Hsapiens.UCSC.hg38.knownGene_3.16.0
## [2] GenomicFeatures_1.50.4
## [3] GenomicRanges_1.50.2
## [4] GenomeInfoDb_1.34.9
## [5] org.Hs.eg.db_3.16.0
## [6] AnnotationDbi_1.60.2
## [7] IRanges_2.32.0
## [8] S4Vectors_0.36.2
## [9] Biobase_2.58.0
## [10] BiocGenerics_0.44.0
## [11] goseq_1.50.0
## [12] geneLenDataBase_1.34.0
## [13] BiasedUrn_2.0.10
## [14] fgsea_1.24.0
## [15] biomaRt_2.54.1
## [16] limma_3.54.2
## [17] tidyr_1.3.0
## [18] ggpubr_0.6.0
## [19] ggplot2_3.4.2
## [20] data.table_1.14.8
##
## loaded via a namespace (and not attached):
## [1] nlme_3.1-162 matrixStats_1.0.0
## [3] bitops_1.0-7 bit64_4.0.5
## [5] filelock_1.0.2 progress_1.2.2
## [7] httr_1.4.6 tools_4.2.3
## [9] backports_1.4.1 bslib_0.4.2
## [11] utf8_1.2.3 R6_2.5.1
## [13] mgcv_1.8-42 DBI_1.1.3
## [15] colorspace_2.1-0 withr_2.5.0
## [17] tidyselect_1.2.0 prettyunits_1.1.1
## [19] bit_4.0.5 curl_5.0.1
## [21] compiler_4.2.3 cli_3.6.1
## [23] xml2_1.3.4 DelayedArray_0.24.0
## [25] rtracklayer_1.58.0 sass_0.4.5
## [27] scales_1.2.1 rappdirs_0.3.3
## [29] Rsamtools_2.14.0 stringr_1.5.0
## [31] digest_0.6.31 rmarkdown_2.21
## [33] XVector_0.38.0 pkgconfig_2.0.3
## [35] htmltools_0.5.5 MatrixGenerics_1.10.0
## [37] dbplyr_2.3.2 fastmap_1.1.1
## [39] rlang_1.1.0 rstudioapi_0.14
## [41] RSQLite_2.3.1 BiocIO_1.8.0
## [43] jquerylib_0.1.4 generics_0.1.3
## [45] jsonlite_1.8.4 BiocParallel_1.32.6
## [47] dplyr_1.1.2 car_3.1-2
## [49] RCurl_1.98-1.12 magrittr_2.0.3
## [51] GO.db_3.16.0 GenomeInfoDbData_1.2.9
## [53] Matrix_1.6-4 Rcpp_1.0.10
## [55] munsell_0.5.0 fansi_1.0.4
## [57] abind_1.4-5 lifecycle_1.0.3
## [59] stringi_1.7.12 yaml_2.3.7
## [61] carData_3.0-5 SummarizedExperiment_1.28.0
## [63] zlibbioc_1.44.0 BiocFileCache_2.6.1
## [65] grid_4.2.3 blob_1.2.4
## [67] parallel_4.2.3 crayon_1.5.2
## [69] lattice_0.20-45 splines_4.2.3
## [71] Biostrings_2.66.0 cowplot_1.1.1
## [73] hms_1.1.3 KEGGREST_1.38.0
## [75] knitr_1.44 pillar_1.9.0
## [77] rjson_0.2.21 ggsignif_0.6.4
## [79] codetools_0.2-19 fastmatch_1.1-3
## [81] XML_3.99-0.14 glue_1.6.2
## [83] evaluate_0.20 png_0.1-8
## [85] vctrs_0.6.2 gtable_0.3.3
## [87] purrr_1.0.1 cachem_1.0.7
## [89] xfun_0.39 broom_1.0.4
## [91] restfulr_0.0.15 rstatix_0.7.2
## [93] tibble_3.2.1 GenomicAlignments_1.34.1
## [95] memoise_2.0.1